Instructions to use mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF",
	filename="Kimi-VL-A3B-Thinking-2506.IQ4_XS.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Kimi-VL-A3B-Thinking-2506-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on Sep 17, 2025

Commit

abcc7e9

verified ·

1 Parent(s): 448f3a6

auto-patch README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -37,6 +37,8 @@ more details, including on how to concatenate multi-part files.
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
 | [GGUF](https://huggingface.co/mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF/resolve/main/Kimi-VL-A3B-Thinking-2506.Q2_K.gguf) | Q2_K | 6.7 |  |
 | [GGUF](https://huggingface.co/mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF/resolve/main/Kimi-VL-A3B-Thinking-2506.Q3_K_S.gguf) | Q3_K_S | 7.7 |  |
 | [GGUF](https://huggingface.co/mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF/resolve/main/Kimi-VL-A3B-Thinking-2506.Q3_K_M.gguf) | Q3_K_M | 8.4 | lower quality |

 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF/resolve/main/Kimi-VL-A3B-Thinking-2506.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement |
+| [GGUF](https://huggingface.co/mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF/resolve/main/Kimi-VL-A3B-Thinking-2506.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement |
 | [GGUF](https://huggingface.co/mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF/resolve/main/Kimi-VL-A3B-Thinking-2506.Q2_K.gguf) | Q2_K | 6.7 |  |
 | [GGUF](https://huggingface.co/mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF/resolve/main/Kimi-VL-A3B-Thinking-2506.Q3_K_S.gguf) | Q3_K_S | 7.7 |  |
 | [GGUF](https://huggingface.co/mradermacher/Kimi-VL-A3B-Thinking-2506-GGUF/resolve/main/Kimi-VL-A3B-Thinking-2506.Q3_K_M.gguf) | Q3_K_M | 8.4 | lower quality |